wassname/openrouter-python-sdk-retry-errors
1
0
Fork 0
mirror of https://github.com/wassname/openrouter-python-sdk-retry-errors.git synced 2026-07-31 12:30:30 +08:00
Code Issues Packages Projects Releases Wiki Activity
Files
d06237bfdec9dc630d968b5e81c9e39695a360d5
openrouter-python-sdk-retry…/.speakeasy/out.openapi.yaml
T
Sheldon Vaughn ab530a160e first commit
2025-08-22 10:31:13 -05:00

1600 lines
48 KiB
YAML
Raw Blame History

openapi: 3.0.0
info:
title: OpenRouter Chat Completions API
version: 1.0.0
description: OpenAI-compatible Chat Completions API with additional OpenRouter features
contact:
name: OpenRouter Support
url: https://openrouter.ai/docs
email: support@openrouter.ai
license:
name: MIT
url: https://opensource.org/licenses/MIT
servers:
- url: https://{provider_url}/api/v1
variables:
provider_url:
default: openrouter.ai
description: Production server
security:
- BearerAuth: []
tags:
- name: Chat
description: Chat completion operations
externalDocs:
description: OpenRouter Documentation
url: https://openrouter.ai/docs
components:
securitySchemes:
BearerAuth:
type: http
scheme: bearer
description: API key as bearer token in Authorization header
schemas:
ChatCompletionMessageToolCall:
type: object
properties:
id:
type: string
description: Tool call identifier
type:
type: string
enum:
- function
function:
type: object
properties:
name:
type: string
description: Function name to call
arguments:
type: string
description: Function arguments as JSON string
required:
- name
- arguments
required:
- id
- type
- function
description: Tool call made by the assistant
ReasoningDetailSummary:
type: object
properties:
type:
type: string
enum:
- reasoning.summary
summary:
type: string
id:
type: string
nullable: true
format:
type: string
nullable: true
enum:
- unknown
- openai-responses-v1
- anthropic-claude-v1
default: anthropic-claude-v1
index:
type: number
required:
- type
- summary
description: Reasoning summary detail
ReasoningDetailEncrypted:
type: object
properties:
type:
type: string
enum:
- reasoning.encrypted
data:
type: string
id:
type: string
nullable: true
format:
type: string
nullable: true
enum:
- unknown
- openai-responses-v1
- anthropic-claude-v1
default: anthropic-claude-v1
index:
type: number
required:
- type
- data
description: Encrypted reasoning detail
ReasoningDetailText:
type: object
properties:
type:
type: string
enum:
- reasoning.text
text:
type: string
nullable: true
signature:
type: string
nullable: true
id:
type: string
nullable: true
format:
type: string
nullable: true
enum:
- unknown
- openai-responses-v1
- anthropic-claude-v1
default: anthropic-claude-v1
index:
type: number
required:
- type
description: Text reasoning detail
ReasoningDetail:
oneOf:
- $ref: '#/components/schemas/ReasoningDetailSummary'
- $ref: '#/components/schemas/ReasoningDetailEncrypted'
- $ref: '#/components/schemas/ReasoningDetailText'
discriminator:
propertyName: type
mapping:
reasoning.summary: '#/components/schemas/ReasoningDetailSummary'
reasoning.encrypted: '#/components/schemas/ReasoningDetailEncrypted'
reasoning.text: '#/components/schemas/ReasoningDetailText'
description: Reasoning detail information
FileAnnotationDetail:
type: object
properties:
type:
type: string
enum:
- file
file:
type: object
properties:
hash:
type: string
name:
type: string
content:
type: array
items:
anyOf:
- type: object
properties:
type:
type: string
enum:
- text
text:
type: string
required:
- type
- text
- type: object
properties:
type:
type: string
enum:
- image_url
image_url:
type: object
properties:
url:
type: string
required:
- url
required:
- type
- image_url
required:
- hash
- content
required:
- type
- file
description: File annotation with content
URLCitationAnnotationDetail:
type: object
properties:
type:
type: string
enum:
- url_citation
url_citation:
type: object
properties:
end_index:
type: number
start_index:
type: number
title:
type: string
url:
type: string
content:
type: string
required:
- end_index
- start_index
- title
- url
required:
- type
- url_citation
description: URL citation annotation
AnnotationDetail:
oneOf:
- $ref: '#/components/schemas/FileAnnotationDetail'
- $ref: '#/components/schemas/URLCitationAnnotationDetail'
discriminator:
propertyName: type
mapping:
file: '#/components/schemas/FileAnnotationDetail'
url_citation: '#/components/schemas/URLCitationAnnotationDetail'
description: Annotation information
ChatCompletionMessage:
type: object
properties:
role:
type: string
enum:
- assistant
content:
type: string
nullable: true
description: Message content
reasoning:
type: string
nullable: true
description: Reasoning output
refusal:
type: string
nullable: true
description: Refusal message if content was refused
tool_calls:
type: array
items:
$ref: '#/components/schemas/ChatCompletionMessageToolCall'
description: Tool calls made by the assistant
reasoning_details:
type: array
items:
$ref: '#/components/schemas/ReasoningDetail'
description: Reasoning details delta to send reasoning details back to upstream
annotations:
type: array
items:
$ref: '#/components/schemas/AnnotationDetail'
description: Annotations delta to send annotations back to upstream
required:
- role
- content
- refusal
description: Assistant message in completion response
ChatCompletionTokenLogprob:
type: object
properties:
token:
type: string
description: The token
logprob:
type: number
description: Log probability of the token
bytes:
type: array
nullable: true
items:
type: number
description: UTF-8 bytes of the token
top_logprobs:
type: array
items:
type: object
properties:
token:
type: string
logprob:
type: number
bytes:
type: array
nullable: true
items:
type: number
required:
- token
- logprob
- bytes
description: Top alternative tokens with probabilities
required:
- token
- logprob
- bytes
- top_logprobs
description: Token log probability information
ChatCompletionTokenLogprobs:
type: object
nullable: true
properties:
content:
type: array
nullable: true
items:
$ref: '#/components/schemas/ChatCompletionTokenLogprob'
description: Log probabilities for content tokens
refusal:
type: array
nullable: true
items:
$ref: '#/components/schemas/ChatCompletionTokenLogprob'
description: Log probabilities for refusal tokens
required:
- content
- refusal
description: Log probabilities for the completion
ChatCompletionChoice:
type: object
properties:
finish_reason:
type: string
nullable: true
enum:
- tool_calls
- stop
- length
- content_filter
- error
description: Reason the completion finished
index:
type: number
description: Choice index
message:
$ref: '#/components/schemas/ChatCompletionMessage'
logprobs:
$ref: '#/components/schemas/ChatCompletionTokenLogprobs'
required:
- finish_reason
- index
- message
description: Chat completion choice
CompletionUsage:
type: object
properties:
completion_tokens:
type: number
description: Number of tokens in the completion
prompt_tokens:
type: number
description: Number of tokens in the prompt
total_tokens:
type: number
description: Total number of tokens
completion_tokens_details:
type: object
properties:
reasoning_tokens:
type: number
description: Tokens used for reasoning
audio_tokens:
type: number
description: Tokens used for audio output
accepted_prediction_tokens:
type: number
description: Accepted prediction tokens
rejected_prediction_tokens:
type: number
description: Rejected prediction tokens
description: Detailed completion token usage
prompt_tokens_details:
type: object
properties:
cached_tokens:
type: number
description: Cached prompt tokens
audio_tokens:
type: number
description: Audio input tokens
description: Detailed prompt token usage
required:
- completion_tokens
- prompt_tokens
- total_tokens
description: Token usage statistics
ChatCompletion:
type: object
properties:
id:
type: string
description: Unique completion identifier
choices:
type: array
items:
$ref: '#/components/schemas/ChatCompletionChoice'
description: List of completion choices
created:
type: number
description: Unix timestamp of creation
model:
type: string
description: Model used for completion
object:
type: string
enum:
- chat.completion
system_fingerprint:
type: string
description: System fingerprint
nullable: true
usage:
$ref: '#/components/schemas/CompletionUsage'
required:
- id
- choices
- created
- model
- object
description: Chat completion response
ChatCompletionError:
type: object
properties:
error:
type: object
properties:
code:
type: string
nullable: true
message:
type: string
param:
type: string
nullable: true
type:
type: string
required:
- code
- message
- param
- type
description: Error object structure
required:
- error
description: Chat completion error response
ChatCompletionChunkChoiceDeltaToolCall:
type: object
properties:
index:
type: number
description: Tool call index in the array
id:
type: string
description: Tool call identifier
type:
type: string
enum:
- function
description: Tool call type
function:
type: object
properties:
name:
type: string
description: Function name
arguments:
type: string
description: Function arguments as JSON string
description: Function call details
required:
- index
description: Tool call delta for streaming responses
ChatCompletionChunkChoiceDelta:
type: object
properties:
role:
type: string
enum:
- assistant
description: The role of the message author
content:
type: string
nullable: true
description: Message content delta
reasoning:
type: string
nullable: true
description: Reasoning content delta
refusal:
type: string
nullable: true
description: Refusal message delta
tool_calls:
type: array
items:
$ref: '#/components/schemas/ChatCompletionChunkChoiceDeltaToolCall'
description: Tool calls delta
reasoning_details:
type: array
items:
$ref: '#/components/schemas/ReasoningDetail'
description: Reasoning details delta to send reasoning details back to upstream
annotations:
type: array
items:
$ref: '#/components/schemas/AnnotationDetail'
description: Annotations delta to send annotations back to upstream
description: Delta changes in streaming response
ChatCompletionChunkChoice:
type: object
properties:
delta:
$ref: '#/components/schemas/ChatCompletionChunkChoiceDelta'
finish_reason:
type: string
nullable: true
enum:
- tool_calls
- stop
- length
- content_filter
- error
index:
type: number
logprobs:
$ref: '#/components/schemas/ChatCompletionTokenLogprobs'
required:
- delta
- finish_reason
- index
description: Streaming completion choice chunk
ChatCompletionChunk:
type: object
properties:
id:
type: string
choices:
type: array
items:
$ref: '#/components/schemas/ChatCompletionChunkChoice'
created:
type: number
model:
type: string
object:
type: string
enum:
- chat.completion.chunk
system_fingerprint:
type: string
nullable: true
usage:
$ref: '#/components/schemas/CompletionUsage'
required:
- id
- choices
- created
- model
- object
description: Streaming chat completion chunk
ChatCompletionRole:
type: string
enum:
- system
- user
- assistant
- tool
- developer
description: The role of the message author
ChatCompletionContentPartText:
type: object
properties:
type:
type: string
enum:
- text
text:
type: string
required:
- type
- text
description: Text content part
ChatCompletionContentPartImage:
type: object
properties:
type:
type: string
enum:
- image_url
image_url:
type: object
properties:
url:
type: string
description: 'URL of the image (data: URLs supported)'
detail:
type: string
enum:
- auto
- low
- high
description: Image detail level for vision models
required:
- url
required:
- type
- image_url
description: Image content part for vision models
ChatCompletionContentPartAudio:
type: object
properties:
type:
type: string
enum:
- input_audio
input_audio:
type: object
properties:
data:
type: string
description: Base64 encoded audio data
format:
type: string
enum:
- wav
- mp3
- flac
- m4a
- ogg
- pcm16
- pcm24
description: Audio format
required:
- data
- format
required:
- type
- input_audio
description: Audio input content part
ChatCompletionContentPart:
oneOf:
- $ref: '#/components/schemas/ChatCompletionContentPartText'
- $ref: '#/components/schemas/ChatCompletionContentPartImage'
- $ref: '#/components/schemas/ChatCompletionContentPartAudio'
discriminator:
propertyName: type
mapping:
text: '#/components/schemas/ChatCompletionContentPartText'
image_url: '#/components/schemas/ChatCompletionContentPartImage'
input_audio: '#/components/schemas/ChatCompletionContentPartAudio'
description: Content part for chat completion messages
ChatCompletionSystemMessageParam:
type: object
properties:
role:
type: string
enum:
- system
content:
anyOf:
- type: string
- type: array
items:
$ref: '#/components/schemas/ChatCompletionContentPartText'
description: System message content
name:
type: string
description: Optional name for the system message
required:
- role
- content
description: System message for setting behavior
ChatCompletionUserMessageParam:
type: object
properties:
role:
type: string
enum:
- user
content:
anyOf:
- type: string
- type: array
items:
$ref: '#/components/schemas/ChatCompletionContentPart'
description: User message content
name:
type: string
description: Optional name for the user
required:
- role
- content
description: User message
ChatCompletionAssistantMessageParam:
type: object
properties:
role:
type: string
enum:
- assistant
content:
anyOf:
- type: string
- type: array
items:
$ref: '#/components/schemas/ChatCompletionContentPart'
- nullable: true
description: Assistant message content
name:
type: string
description: Optional name for the assistant
tool_calls:
type: array
items:
$ref: '#/components/schemas/ChatCompletionMessageToolCall'
description: Tool calls made by the assistant
refusal:
type: string
nullable: true
description: Refusal message if content was refused
required:
- role
description: Assistant message with tool calls and audio support
ChatCompletionToolMessageParam:
type: object
properties:
role:
type: string
enum:
- tool
content:
anyOf:
- type: string
- type: array
items:
$ref: '#/components/schemas/ChatCompletionContentPart'
description: Tool response content
tool_call_id:
type: string
description: ID of the tool call this message responds to
required:
- role
- content
- tool_call_id
description: Tool response message
ChatCompletionMessageParam:
oneOf:
- $ref: '#/components/schemas/ChatCompletionSystemMessageParam'
- $ref: '#/components/schemas/ChatCompletionUserMessageParam'
- $ref: '#/components/schemas/ChatCompletionAssistantMessageParam'
- $ref: '#/components/schemas/ChatCompletionToolMessageParam'
discriminator:
propertyName: role
mapping:
system: '#/components/schemas/ChatCompletionSystemMessageParam'
user: '#/components/schemas/ChatCompletionUserMessageParam'
assistant: '#/components/schemas/ChatCompletionAssistantMessageParam'
tool: '#/components/schemas/ChatCompletionToolMessageParam'
description: Chat completion message with role-based discrimination
ChatCompletionTool:
type: object
properties:
type:
type: string
enum:
- function
function:
type: object
properties:
name:
type: string
maxLength: 64
description: Function name (a-z, A-Z, 0-9, underscores, dashes, max 64 chars)
description:
type: string
description: Function description for the model
parameters:
type: object
properties: {}
description: Function parameters as JSON Schema object
strict:
type: boolean
nullable: true
description: Enable strict schema adherence
required:
- name
description: Function definition for tool calling
required:
- type
- function
description: Tool definition for function calling
ChatCompletionNamedToolChoice:
type: object
properties:
type:
type: string
enum:
- function
function:
type: object
properties:
name:
type: string
description: Function name to call
required:
- name
required:
- type
- function
description: Named tool choice for specific function
ChatCompletionToolChoiceOption:
anyOf:
- type: string
enum:
- none
- type: string
enum:
- auto
- type: string
enum:
- required
- $ref: '#/components/schemas/ChatCompletionNamedToolChoice'
description: Tool choice configuration
ChatCompletionStreamOptions:
type: object
properties:
include_usage:
type: boolean
description: Include usage information in streaming response
description: Streaming configuration options
ResponseFormatJsonSchemaSchema:
type: object
properties: {}
description: The schema for the response format, described as a JSON Schema object
ChatCompletionCreateParams:
type: object
properties:
messages:
type: array
items:
$ref: '#/components/schemas/ChatCompletionMessageParam'
minItems: 1
description: List of messages for the conversation
example:
- role: user
content: Hello, how are you?
model:
type: string
description: Model to use for completion
frequency_penalty:
type: number
nullable: true
minimum: -2
maximum: 2
description: Frequency penalty (-2.0 to 2.0)
logit_bias:
type: object
nullable: true
additionalProperties:
type: number
description: Token logit bias adjustments
logprobs:
type: boolean
nullable: true
description: Return log probabilities
top_logprobs:
type: number
nullable: true
minimum: 0
maximum: 20
description: Number of top log probabilities to return (0-20)
max_completion_tokens:
type: number
nullable: true
minimum: 1
description: Maximum tokens in completion
max_tokens:
type: number
nullable: true
minimum: 1
description: Maximum tokens (deprecated, use max_completion_tokens)
metadata:
type: object
additionalProperties:
type: string
description: Key-value pairs for additional object information (max 16 pairs, 64 char keys, 512 char values)
presence_penalty:
type: number
nullable: true
minimum: -2
maximum: 2
description: Presence penalty (-2.0 to 2.0)
reasoning:
type: object
nullable: true
properties:
enabled:
type: boolean
description: Enables reasoning with default settings. Only work for some models.
effort:
type: string
nullable: true
enum:
- high
- medium
- low
- minimal
description: OpenAI-style reasoning effort setting
max_tokens:
type: number
nullable: true
description: non-OpenAI-style reasoning effort setting
exclude:
type: boolean
default: false
description: Reasoning configuration
response_format:
oneOf:
- type: object
properties:
type:
type: string
enum:
- text
required:
- type
description: Default text response format
- type: object
properties:
type:
type: string
enum:
- json_object
required:
- type
description: JSON object response format
- type: object
properties:
type:
type: string
enum:
- json_schema
json_schema:
type: object
properties:
name:
type: string
maxLength: 64
description: Schema name (a-z, A-Z, 0-9, underscores, dashes, max 64 chars)
description:
type: string
description: Schema description for the model
schema:
$ref: '#/components/schemas/ResponseFormatJsonSchemaSchema'
strict:
type: boolean
nullable: true
description: Enable strict schema adherence
required:
- name
required:
- type
- json_schema
description: JSON Schema response format for structured outputs
- type: object
properties:
type:
type: string
enum:
- grammar
grammar:
type: string
description: Custom grammar for text generation
required:
- type
- grammar
description: Custom grammar response format
- type: object
properties:
type:
type: string
enum:
- python
required:
- type
description: Python code response format
description: Response format configuration
seed:
type: integer
nullable: true
description: Random seed for deterministic outputs
stop:
anyOf:
- type: string
- type: array
items:
type: string
maxItems: 4
- nullable: true
description: Stop sequences (up to 4)
stream:
type: boolean
nullable: true
default: false
description: Enable streaming response
stream_options:
allOf:
- $ref: '#/components/schemas/ChatCompletionStreamOptions'
- nullable: true
temperature:
type: number
nullable: true
minimum: 0
maximum: 2
default: 1
description: Sampling temperature (0-2)
tool_choice:
$ref: '#/components/schemas/ChatCompletionToolChoiceOption'
tools:
type: array
items:
$ref: '#/components/schemas/ChatCompletionTool'
description: Available tools for function calling
top_p:
type: number
nullable: true
minimum: 0
maximum: 1
default: 1
description: Nucleus sampling parameter (0-1)
user:
type: string
description: Unique user identifier
models:
x-speakeasy-name-override: models_llm
type: array
nullable: true
items:
type: string
description: Order of models to fallback to for this request
reasoning_effort:
type: string
nullable: true
enum:
- high
- medium
- low
- minimal
description: Reasoning effort
provider:
type: object
nullable: true
properties:
allow_fallbacks:
type: boolean
nullable: true
description: >
Whether to allow backup providers to serve requests
- true: (default) when the primary provider (or your custom providers in "order") is unavailable, use the next best provider.
- false: use only the primary/custom provider, and return the upstream error if it's unavailable.
require_parameters:
type: boolean
nullable: true
description: >-
Whether to filter providers to only those that support the parameters you've provided. If this setting is omitted or set to false, then providers will receive only the parameters they support, and ignore the rest.
data_collection:
type: string
nullable: true
enum:
- deny
- allow
description: >
Data collection setting. If no available model provider meets the requirement, your request will return an error.
- allow: (default) allow providers which store user data non-transiently and may train on it
- deny: use only providers which do not collect user data.
order:
type: array
nullable: true
items:
anyOf:
- type: string
enum:
- AnyScale
- Cent-ML
- HuggingFace
- Hyperbolic 2
- Lepton
- Lynn 2
- Lynn
- Mancer
- Modal
- OctoAI
- Recursal
- Reflection
- Replicate
- SambaNova 2
- SF Compute
- Together 2
- 01.AI
- AI21
- AionLabs
- Alibaba
- Amazon Bedrock
- Anthropic
- AtlasCloud
- Atoma
- Avian
- Azure
- BaseTen
- Cerebras
- Chutes
- Cloudflare
- Cohere
- CrofAI
- Crusoe
- DeepInfra
- DeepSeek
- Enfer
- Featherless
- Fireworks
- Friendli
- GMICloud
- Google
- Google AI Studio
- Groq
- Hyperbolic
- Inception
- InferenceNet
- Infermatic
- Inflection
- InoCloud
- Kluster
- Lambda
- Liquid
- Mancer 2
- Meta
- Minimax
- Mistral
- Moonshot AI
- Morph
- NCompass
- Nebius
- NextBit
- Nineteen
- Novita
- OpenAI
- OpenInference
- Parasail
- Perplexity
- Phala
- SambaNova
- Stealth
- Switchpoint
- Targon
- Together
- Ubicloud
- Venice
- WandB
- xAI
- Z.AI
- type: string
description: >-
An ordered list of provider slugs. The router will attempt to use the first provider in the subset of this list that supports your requested model, and fall back to the next if it is unavailable. If no providers are available, the request will fail with an error message.
only:
type: array
nullable: true
items:
anyOf:
- type: string
enum:
- AnyScale
- Cent-ML
- HuggingFace
- Hyperbolic 2
- Lepton
- Lynn 2
- Lynn
- Mancer
- Modal
- OctoAI
- Recursal
- Reflection
- Replicate
- SambaNova 2
- SF Compute
- Together 2
- 01.AI
- AI21
- AionLabs
- Alibaba
- Amazon Bedrock
- Anthropic
- AtlasCloud
- Atoma
- Avian
- Azure
- BaseTen
- Cerebras
- Chutes
- Cloudflare
- Cohere
- CrofAI
- Crusoe
- DeepInfra
- DeepSeek
- Enfer
- Featherless
- Fireworks
- Friendli
- GMICloud
- Google
- Google AI Studio
- Groq
- Hyperbolic
- Inception
- InferenceNet
- Infermatic
- Inflection
- InoCloud
- Kluster
- Lambda
- Liquid
- Mancer 2
- Meta
- Minimax
- Mistral
- Moonshot AI
- Morph
- NCompass
- Nebius
- NextBit
- Nineteen
- Novita
- OpenAI
- OpenInference
- Parasail
- Perplexity
- Phala
- SambaNova
- Stealth
- Switchpoint
- Targon
- Together
- Ubicloud
- Venice
- WandB
- xAI
- Z.AI
- type: string
description: >-
List of provider slugs to allow. If provided, this list is merged with your account-wide allowed provider settings for this request.
ignore:
type: array
nullable: true
items:
anyOf:
- type: string
enum:
- AnyScale
- Cent-ML
- HuggingFace
- Hyperbolic 2
- Lepton
- Lynn 2
- Lynn
- Mancer
- Modal
- OctoAI
- Recursal
- Reflection
- Replicate
- SambaNova 2
- SF Compute
- Together 2
- 01.AI
- AI21
- AionLabs
- Alibaba
- Amazon Bedrock
- Anthropic
- AtlasCloud
- Atoma
- Avian
- Azure
- BaseTen
- Cerebras
- Chutes
- Cloudflare
- Cohere
- CrofAI
- Crusoe
- DeepInfra
- DeepSeek
- Enfer
- Featherless
- Fireworks
- Friendli
- GMICloud
- Google
- Google AI Studio
- Groq
- Hyperbolic
- Inception
- InferenceNet
- Infermatic
- Inflection
- InoCloud
- Kluster
- Lambda
- Liquid
- Mancer 2
- Meta
- Minimax
- Mistral
- Moonshot AI
- Morph
- NCompass
- Nebius
- NextBit
- Nineteen
- Novita
- OpenAI
- OpenInference
- Parasail
- Perplexity
- Phala
- SambaNova
- Stealth
- Switchpoint
- Targon
- Together
- Ubicloud
- Venice
- WandB
- xAI
- Z.AI
- type: string
description: >-
List of provider slugs to ignore. If provided, this list is merged with your account-wide ignored provider settings for this request.
quantizations:
type: array
nullable: true
items:
type: string
enum:
- int4
- int8
- fp4
- fp6
- fp8
- fp16
- bf16
- fp32
- unknown
description: A list of quantization levels to filter the provider by.
sort:
type: string
nullable: true
enum:
- price
- throughput
- latency
description: >-
The sorting strategy to use for this request, if "order" is not specified. When set, no load balancing is performed.
max_price:
type: object
properties:
prompt:
anyOf:
- type: number
- type: string
- {}
completion:
anyOf:
- type: number
- type: string
- {}
image:
anyOf:
- type: number
- type: string
- {}
audio:
anyOf:
- type: number
- type: string
- {}
request:
anyOf:
- type: number
- type: string
- {}
additionalProperties: false
description: >-
The object specifying the maximum price you want to pay for this request. USD price per million tokens, for prompt and completion.
additionalProperties: false
description: When multiple model providers are available, optionally indicate your routing preference.
plugins:
type: array
items:
oneOf:
- type: object
properties:
id:
type: string
enum:
- moderation
required:
- id
- type: object
properties:
id:
type: string
enum:
- web
max_results:
type: number
search_prompt:
type: string
engine:
type: string
enum:
- native
- exa
required:
- id
- type: object
properties:
id:
type: string
enum:
- chain-of-thought
required:
- id
- type: object
properties:
id:
type: string
enum:
- file-parser
max_files:
type: number
pdf:
type: object
properties:
engine:
type: string
enum:
- mistral-ocr
- pdf-text
- native
required:
- id
description: Plugins you want to enable for this request, including their settings.
required:
- messages
description: Chat completion request parameters
ChatStreamCompletionCreateParams:
allOf:
- $ref: "#/components/schemas/ChatCompletionCreateParams"
- type: object
properties:
stream:
type: boolean
enum:
- true
default: true
description: Enable streaming response
parameters: {}
paths:
/chat/completions:
post:
operationId: createChatCompletion
summary: Create a chat completion
description: Creates a model response for the given chat conversation. Supports both streaming and non-streaming modes.
tags:
- Chat
requestBody:
description: Chat completion request parameters
required: true
content:
application/json:
schema:
$ref: '#/components/schemas/ChatCompletionCreateParams'
responses:
'200':
description: Successful chat completion response
content:
application/json:
schema:
$ref: '#/components/schemas/ChatCompletion'
description: Non-streaming response when stream=false
'400':
description: Bad request - invalid parameters
content:
application/json:
schema:
$ref: '#/components/schemas/ChatCompletionError'
'401':
description: Unauthorized - invalid API key
content:
application/json:
schema:
$ref: '#/components/schemas/ChatCompletionError'
'429':
description: Too many requests - rate limit exceeded
content:
application/json:
schema:
$ref: '#/components/schemas/ChatCompletionError'
'500':
description: Internal server error
content:
application/json:
schema:
$ref: '#/components/schemas/ChatCompletionError'
x-speakeasy-name-override: complete
/chat/completions#stream:
post:
operationId: streamChatCompletion
summary: Create a chat completion
description: Creates a model response for the given chat conversation. Supports both streaming and non-streaming modes.
tags:
- Chat
requestBody:
description: Chat completion request parameters
required: true
content:
application/json:
schema:
$ref: '#/components/schemas/ChatStreamCompletionCreateParams'
responses:
'200':
description: Successful chat completion response
content:
text/event-stream:
x-speakeasy-sse-sentinel: '[DONE]'
schema:
type: object
required: [data]
properties:
data:
$ref: '#/components/schemas/ChatCompletionChunk'
'400':
description: Bad request - invalid parameters
content:
application/json:
schema:
$ref: '#/components/schemas/ChatCompletionError'
'401':
description: Unauthorized - invalid API key
content:
application/json:
schema:
$ref: '#/components/schemas/ChatCompletionError'
'429':
description: Too many requests - rate limit exceeded
content:
application/json:
schema:
$ref: '#/components/schemas/ChatCompletionError'
'500':
description: Internal server error
content:
application/json:
schema:
$ref: '#/components/schemas/ChatCompletionError'
x-speakeasy-name-override: completeStream
Reference in New Issue View Git Blame Copy Permalink